squashfs: add optional full compressed block caching

The commit 93e72b3 ("squashfs: migrate from ll_rw_block usage
to BIO") removed caching of compressed blocks in SquashFS, causing fio
performance regression in workloads with repeated file reads.  Without
caching, every read triggers disk I/O, severely impacting performance in
tools like fio.

This patch introduces a new CONFIG_SQUASHFS_COMP_CACHE_FULL Kconfig option
to enable caching of all compressed blocks, restoring performance to
pre-BIO migration levels.  When enabled, all pages in a BIO are cached in
the page cache, reducing disk I/O for repeated reads.  The fio test
results with this patch confirm the performance restoration:

For example, fio tests (iodepth=1, numjobs=1,
ioengine=psync) show a notable performance restoration:

Disable CONFIG_SQUASHFS_COMP_CACHE_FULL:
  IOPS=815, BW=102MiB/s (107MB/s)(6113MiB/60001msec)
Enable CONFIG_SQUASHFS_COMP_CACHE_FULL:
  IOPS=2223, BW=278MiB/s (291MB/s)(16.3GiB/59999msec)

The tradeoff is increased memory usage due to caching all compressed
blocks.  The CONFIG_SQUASHFS_COMP_CACHE_FULL option allows users to enable
this feature selectively, balancing performance and memory usage for
workloads with frequent repeated reads.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Chanho Min <[email protected]>
Reviewed-by Phillip Lougher <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: Chanho Min

fs/squashfs/Kconfig

@@ -149,6 +149,27 @@ config SQUASHFS_XATTR
 
 	  If unsure, say N.
 
+config SQUASHFS_COMP_CACHE_FULL
+	bool "Enable full caching of compressed blocks"
+	depends on SQUASHFS
+	default n
+	help
+	  This option enables caching of all compressed blocks, Without caching,
+	  repeated reads of the same files trigger excessive disk I/O, significantly
+	  reducinng performance in workloads like fio-based benchmarks.
+
+	  For example, fio tests (iodepth=1, numjobs=1, ioengine=psync) show:
+	   With caching: IOPS=2223, BW=278MiB/s (291MB/s)
+	   Without caching: IOPS=815, BW=102MiB/s (107MB/s)
+
+	  Enabling this option restores performance to pre-regression levels by
+	  caching all compressed blocks in the page cache, reducing disk I/O for
+	  repeated reads. However, this increases memory usage, which may be a
+	  concern in memory-constrained environments.
+
+	  Enable this option if your workload involves frequent repeated reads and
+	  memory usage is not a limiting factor. If unsure, say N.
+
 config SQUASHFS_ZLIB
 	bool "Include support for ZLIB compressed file systems"
 	depends on SQUASHFS

fs/squashfs/block.c

@@ -88,6 +88,10 @@ static int squashfs_bio_read_cached(struct bio *fullbio,
 	struct bio_vec *bv;
 	int idx = 0;
 	int err = 0;
+#ifdef CONFIG_SQUASHFS_COMP_CACHE_FULL
+	struct page **cache_pages = kmalloc_array(page_count,
+			sizeof(void *), GFP_KERNEL | __GFP_ZERO);
+#endif
 
 	bio_for_each_segment_all(bv, fullbio, iter_all) {
 		struct page *page = bv->bv_page;
@@ -110,6 +114,11 @@ static int squashfs_bio_read_cached(struct bio *fullbio,
 			head_to_cache = page;
 		else if (idx == page_count - 1 && index + length != read_end)
 			tail_to_cache = page;
+#ifdef CONFIG_SQUASHFS_COMP_CACHE_FULL
+		/* Cache all pages in the BIO for repeated reads */
+		else if (cache_pages)
+			cache_pages[idx] = page;
+#endif
 
 		if (!bio || idx != end_idx) {
 			struct bio *new = bio_alloc_clone(bdev, fullbio,
@@ -163,6 +172,25 @@ static int squashfs_bio_read_cached(struct bio *fullbio,
 		}
 	}
 
+#ifdef CONFIG_SQUASHFS_COMP_CACHE_FULL
+	if (!cache_pages)
+		goto out;
+
+	for (idx = 0; idx < page_count; idx++) {
+		if (!cache_pages[idx])
+			continue;
+		int ret = add_to_page_cache_lru(cache_pages[idx], cache_mapping,
+						(read_start >> PAGE_SHIFT) + idx,
+						GFP_NOIO);
+
+		if (!ret) {
+			SetPageUptodate(cache_pages[idx]);
+			unlock_page(cache_pages[idx]);
+		}
+	}
+	kfree(cache_pages);
+out:
+#endif
 	return 0;
 }